See MCP (Model Context Protocol) in action — your AI agent fetches web content, queries Singapore legislation, and connects to data sources in plain English.
⏱ 25 minutes
What You'll Learn
In Lab 1, you built a skill that works with data you paste into the chat. That's fine for prototyping — but in production, your AI agent needs to connect to data sources directly. That's what MCP (Model Context Protocol) does.
📋
Without MCP
You paste data into the chat, or the AI reads files from your workspace. Manual, one-at-a-time.
🔌
With MCP
AI connects to websites, databases, APIs, and legislation directly. Ask in plain English — it fetches the answer.
💡 What is MCP?
Model Context Protocol (MCP) is an open standard that connects AI to external tools and data sources. Think of it as a USB-C port for AI:
MCP Server = the data source (website, database, API, legislation database)
MCP Client = Kiro (the AI that uses the data)
You don't write code — you configure a connection, and the AI can query it
Today you'll see two MCP servers in action: one that fetches web pages, and one that searches Singapore legislation.
Part
Duration
What you'll see
Part A
8 min
Fetch MCP — AI reads AnyCompany's policy page and answers questions about coverage
Part B
12 min
Singapore Law MCP — AI searches the Insurance Act, PDPA, and MAS regulations
Part C
5 min
Vision — what MCP servers would AnyCompany need in production?
Part A: Fetch MCP — AI Reads the Web
Kiro has a built-in Fetch tool that can read any public web page and return its content. No setup needed — it's already available.
🟢 Zero setup required — The Fetch tool is built into Kiro. Just ask it to read a URL.
Scenario: A customer asks about critical illness coverage
Imagine a customer service agent needs to quickly check what's covered under AnyCompany's Critical Illness plan. Instead of searching through internal documents, the AI reads the product page directly:
PROMPT — Copy & paste into Kiro
Fetch the AnyCompany Insurance product guide from this URL:
https://sing.lab.mywcloud.net/anycompany-policies.html
Then answer these questions:
1. How many critical illnesses are covered under AnyCare Critical?
2. What is the maximum sum assured available?
3. If a customer has cancer and recovers, can they claim again if it comes back?
4. What is the survival period requirement?
Format your answers as a clear summary a customer service agent could read to a caller.
✅ What to observe:
Kiro fetches the web page content automatically
It extracts specific answers from the product information
The answers are accurate — grounded in the actual page content, not hallucinated
It formats the response for the intended audience (customer service agent)
Try another query — comparing products:
PROMPT — Product comparison
Based on the AnyCompany product guide you just read, create a comparison table for a customer who is deciding between the three AnyCare Shield tiers (Basic, Enhanced, Premier).
Focus on: annual claim limit, ward class, daily room & board, and annual premium for a 30-year-old.
Add a recommendation at the bottom: which tier suits (a) a budget-conscious young professional, (b) a family breadwinner, and (c) a high-net-worth individual?
💡 Why this matters for AnyCompany:
Today, your customer service team searches through PDF product brochures or internal wikis to answer questions. With Fetch MCP, an AI agent can read your product pages, policy documents, or even competitor websites — and synthesize answers in seconds. This is the foundation for an intelligent customer service agent.
Part B: Singapore Law MCP — AI Searches Legislation
Now let's connect a more powerful MCP server — one that searches across 523 Singapore Acts including the Insurance Act, PDPA, Financial Advisers Act, and MAS regulations.
523 Acts from Singapore Statutes Online (Attorney-General's Chambers)
28,045 provisions — full-text searchable
13 tools including search, citation validation, and legal stance building
Data sourced from official Singapore Statutes Online (sso.agc.gov.sg)
Step 1: Configure the MCP connection
In Kiro, open the MCP configuration. Ask Kiro to add the Singapore Law server:
PROMPT — Add MCP server
Add a new MCP server to my configuration. The server is called "singaporean-law" and runs via npx:
Command: npx
Args: ["-y", "@ansvar/singapore-law-mcp"]
Add it to my MCP config file.
📁 What this does: Kiro adds the server to .kiro/settings/mcp.json. The npx command downloads and runs the server automatically — no manual installation needed. Once connected, Kiro gains 13 new tools for searching Singapore legislation.
✅ Checkpoint: After adding the config, Kiro should reconnect to MCP servers. You can verify by checking the MCP panel (Kiro icon → MCP Servers) — you should see "singaporean-law" listed with its tools.
Step 2: Query insurance-relevant legislation
Now ask questions about Singapore insurance law — in plain English:
PROMPT — Insurance Act query
Using the Singapore Law MCP, search for provisions in the Insurance Act related to:
1. Policy surrender values — what are the requirements for insurers?
2. Nomination of beneficiaries — how does the Insurance Act handle this?
3. What does the Act say about the "free-look" or cooling-off period?
For each finding, give me the exact section number and a plain-English summary of what it means for AnyCompany's operations.
PROMPT — PDPA and insurance data
Search Singapore legislation for provisions about:
1. What does the PDPA say about collecting health data for insurance underwriting?
2. Are there exceptions that allow insurers to use personal data without consent?
3. What are the data breach notification requirements that would apply to an insurance company?
Cite the specific Act and section for each answer.
PROMPT — Compliance scenario
AnyCompany Insurance wants to launch a new AI-powered underwriting system that automatically assesses health risk from customer-submitted medical records.
Using Singapore legislation, help me understand:
1. What PDPA provisions govern the automated processing of health data?
2. Are there any Insurance Act requirements about how underwriting decisions must be communicated?
3. What does the Financial Advisers Act say about disclosure when using automated systems?
Build a brief compliance checklist based on the legislation you find.
🔍 What to observe:
The AI searches across multiple Acts (Insurance Act, PDPA, Financial Advisers Act)
It returns specific section numbers — not vague summaries
It cross-references between Acts when relevant
The answers are grounded in actual legislation, not general knowledge
💡 Compare this to today's workflow:
Current approach
With MCP
Search
Open SSO website → navigate to Act → Ctrl+F
"Search for provisions about beneficiary nominations"
Cross-reference
Open multiple browser tabs, manually compare
"What do both the Insurance Act and PDPA say about this?"
Summarize
Read 50 sections, write your own summary
"Give me a compliance checklist based on the legislation"
Time
30–60 minutes per research question
30 seconds
Part C: What MCP Servers Would AnyCompany Need?
You've seen two MCP servers in action. In production, AnyCompany would connect AI agents to many more data sources — all through the same MCP protocol.
🏗️ AnyCompany's MCP Architecture (Vision)
MCP Server
What it connects to
Example queries
Policy Admin
Core policy system (Oracle/SAP)
"Show all policies lapsing this month" · "What's the status of POL-2024-8847?"
Claims System
Claims management platform
"List all pending claims over $50K" · "Average processing time for critical illness claims?"
Customer 360
CRM + interaction history
"Full profile for customer CUST-88421" · "Customers with 3+ policies not contacted in 6 months"
Singapore Law
Legislation database (SSO)
"Insurance Act requirements for policy illustrations" · "PDPA consent for health data"
MAS Circulars
Regulatory notices & guidelines
"Latest MAS notice on technology risk management" · "Fair Dealing outcome requirements"
Actuarial Models
Pricing & reserving systems
"Current mortality rates for age 45 male non-smoker" · "IFRS 17 reserve for product X"
Document Store
Policy documents, medical reports
"Retrieve the medical report for claim CLM-2024-0847" · "Find the policy contract for POL-123"
Web / Fetch
Public websites, competitor info
"Read the latest MAS media release" · "Compare our CI coverage with competitor X"
Each MCP server is built and maintained by the team that owns that data source. The AI agent decides which server to query based on the question — just like a human would know which system to check.
🎯 For the Agent Design Canvas (Lab 3)
When you fill in the "Data Sources" section of your Agent Design Canvas, think about which MCP servers your agent would need. The pattern is always the same:
What data does the agent need to do its job?
Where does that data live today? (database, API, website, document)
That becomes an MCP server connection
🌐 MCP is growing fast
The MCP ecosystem already has hundreds of servers for different data sources:
Databases: PostgreSQL, MySQL, SQLite, MongoDB
APIs: Slack, Jira, GitHub, Salesforce, ServiceNow
Documents: Google Drive, SharePoint, Confluence
Specialized: Singapore Law, AWS Documentation, financial data feeds
Your tech team doesn't need to build everything from scratch — many MCP servers already exist. For custom internal systems, building an MCP server is typically a few hundred lines of code.
📋 Summary: The MCP Stack
Layer
What it does
You saw this in
Steering
Global rules (currency, PII, ratings)
Lab 1, Step 1
Skills
On-demand expertise (risk assessment, compliance)
Lab 1, Steps 2-5
Hooks
Auto-triggers (new file → run skill)
Lab 1, Step 3
MCP
Data connections (web, legislation, databases)
This lab
🎉 What You've Seen
Fetch MCP — AI reading a web page and extracting structured answers about insurance products
Singapore Law MCP — AI searching 523 Acts and returning specific provisions with citations
The MCP pattern — same protocol, different data sources, AI decides which to query
Production vision — how AnyCompany would connect AI to policy admin, claims, CRM, and regulatory systems
💡 Key takeaway for your team
MCP turns AI from a "chatbot that knows general things" into a "system that can query YOUR data." The protocol is open, the ecosystem is growing, and the setup is configuration — not custom development. When you design your agent in Lab 3, think about what data sources it needs. Each one becomes an MCP connection.